This is part of the Pistoia Alliance Collaborate to Innovate Virtual Conference Week, October 19-23, 2020.  For more information about related events, please visit our online calendar.

Summary

Unsupervised embedding techniques have been shown to capture complex concepts from unstructured data such as published texts and electronic health records. Applying these machine learning methods to structured, expert-curated content from the scientific literature can be even more powerful.

Building on the QIAGEN Knowledge Base, we use this approach to infer new disease-gene associations and build disease models that can be applied to drug repurposing. The presentation will focus on a case study in which new SARS-CoV-2 research was combined with a knowledge graph and machine learning models to create the Coronavirus Network Explorer, a free collection of interactive networks depicting how viral proteins interact with host proteins to impact a variety of host cell functions.

Learning Objectives

At the conclusion of this session, participants should be able to:

• Recognize the value of combining machine learning techniques with curated data organized into a knowledge graph to uncover latent knowledge

• Explore how SARS-CoV-2 proteins interact with host proteins and the linked downstream effects

• Identify existing drugs that could impact the effects of the virus according to predicted models

Featured Topics

• QIAGEN Digital Insights (QDI) has a unique, valuable resource in the QIAGEN Knowledge Base (KB) which is used to produce a knowledge graph, causally linking genes, pathways, biological functions, and diseases

• QDI is leveraging Machine Learning techniques in a novel way to uncover latent knowledge in the knowledge graph

• The combination of the knowledge graph, machine learning approaches, and experimental datasets can produce valuable, novel insights via graphical exploration tools such as the Coronavirus Network Explorer

Sponsored by: 

Jonathan Sheldon Senior Vice President, QIAGEN Digital Insights Business Area

Register for the Conference

October 19-23, 2020